Font Size: a A A

Analysis And Comparison On Image Reconstruction Algorithms For Electrical Capacitance Tomography

Posted on:2007-08-19Degree:MasterType:Thesis
Country:ChinaCandidate:H Y LiuFull Text:PDF
GTID:2178360185989434Subject:Computer software and theory
Abstract/Summary:PDF Full Text Request
Multiphase flow system is a complex, nonlinear system. There are interface effect and relative velocity between these multiphase flows. That causes the difficult of measurement of multiphase flow. In the world, the multiphase flow is an exploration research field, which is waited to develop urgently. Process Tomography (PT) technique, which is has been developed rapidly in recent ten years, has great developmental potential and wide industrial application prospect. Electrical Capacitance Tomography (ECT) has many distinct advantages such as low cost, wide application field, simple structure, non-invasive measurement and better safety, ECT has being the most popular research direction and the main development in process tomography technique. There is still a lot of work to be done before practical use of the technique. Support Vector Machines (SVM) is a kind of novel machine learning methods. It can solve small-sample learning problems better by using Experiential Risk Minimization in place of Structural Risk Minimization. Moreover, this theory can change the problem in non-linearity space to that in the linearity space in order to reduce the algorithm complexity by using the kernel function idea's have become the hotspot of machine learning because of their excellent learning performance. They also have successful applications in many fields, such as face detection, handwriting digit recognition, text auto-categorization.The objective study in this paper is major in the ECT system of 8-electrode.It taken into account the good generalization of support vector machine in small samples, nonlinearity and high dimension space, studies the identification problem of flow regimes in oil/water two-phase flows. Meanwhile, projection data is obtained to do image reconstructions for typical flow regimes based on the SVM image reconstruction algorithm. The main study content and fruit is listed as follows:1. The paper introduces the basic principles of tomography, the system constitution, the basic features, developing status and the process tomography based on various sensing technique. It also analyzes the principle and proposes the mathematical...
Keywords/Search Tags:electrical capacitance tomography, support vector machines, kernel function, image reconstruction algorithms
PDF Full Text Request
Related items